Training in progress, step 890000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da5e919e619fc37caeb953290b94918647456cda690ed7144cc7178be39d996
+oid sha256:42ed7fe58b215bb0dbec2af4a7d664e938d635b1ef05290da2036605b37704a3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad82584973d0520c6413d732f42ff58e62845f5cbb51b8e6c61b5efa59935b29
+oid sha256:aa4ab0c6834a759e55baa287a48208abf39c778ed277af3b0afe1b1b96d8b552
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8247214429488e1ea2f48554aadf9d9e15296edc93a8c054713ad6895a659c39
+oid sha256:f483f771a26716cfd70c3a5175a315dd25e3cc6dc8bc56308db21f3af0dc88d6
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117f7d200093f36e829666009e11215a545656db39c99ea467c0382946c51c22
+oid sha256:5b2fa8647e8771b01ebc4433e88606f474979e505ff0f89ae2bd75e3418c26e7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f55aebb09939f1fc3dd2058ded88566ba4348e9d7ff44ef41bb43747cfc1b0
+oid sha256:70df957d931b4b06dbdec01474740c6119583917c674231d25b7b12875e1d7a9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b627f03b99c458439f40d3224dc9c96157642aba0d132f2a4952c2022aee879
-size 14439
+oid sha256:bbaae9451e4051ab9fe7948d1d8a9c41e70f70568605abb0409e412d5e85feaa
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebaa6261431616bb924fa3611c1e782327703255936f9b7e34a1eda29c117895
+oid sha256:2afa6aa14483adb7c817c2439178a198c4680dbfe427eab82def33bea1566914
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.437781544428665,
-  "global_step": 880000,
+  "epoch": 13.590483607433537,
+  "global_step": 890000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6518,11 +6518,85 @@
       "eval_samples_per_second": 1164.009,
       "eval_steps_per_second": 18.624,
       "step": 880000
+    },
+    {
+      "epoch": 13.45,
+      "learning_rate": 1.535060126557028e-05,
+      "loss": 0.2322,
+      "step": 881000
+    },
+    {
+      "epoch": 13.47,
+      "learning_rate": 1.5262192375024284e-05,
+      "loss": 0.232,
+      "step": 882000
+    },
+    {
+      "epoch": 13.48,
+      "learning_rate": 1.5174491446770566e-05,
+      "loss": 0.2314,
+      "step": 883000
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 1.508749943989242e-05,
+      "loss": 0.2312,
+      "step": 884000
+    },
+    {
+      "epoch": 13.51,
+      "learning_rate": 1.500121730572051e-05,
+      "loss": 0.2314,
+      "step": 885000
+    },
+    {
+      "epoch": 13.51,
+      "eval_runtime": 0.7508,
+      "eval_samples_per_second": 1331.906,
+      "eval_steps_per_second": 21.31,
+      "step": 885000
+    },
+    {
+      "epoch": 13.53,
+      "learning_rate": 1.4915645987822406e-05,
+      "loss": 0.2314,
+      "step": 886000
+    },
+    {
+      "epoch": 13.54,
+      "learning_rate": 1.4830786421992347e-05,
+      "loss": 0.2316,
+      "step": 887000
+    },
+    {
+      "epoch": 13.56,
+      "learning_rate": 1.4746639536240942e-05,
+      "loss": 0.2312,
+      "step": 888000
+    },
+    {
+      "epoch": 13.58,
+      "learning_rate": 1.4663206250785055e-05,
+      "loss": 0.2315,
+      "step": 889000
+    },
+    {
+      "epoch": 13.59,
+      "learning_rate": 1.4580487478037748e-05,
+      "loss": 0.2311,
+      "step": 890000
+    },
+    {
+      "epoch": 13.59,
+      "eval_runtime": 0.7331,
+      "eval_samples_per_second": 1364.004,
+      "eval_steps_per_second": 21.824,
+      "step": 890000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.168814428784615e+22,
+  "total_flos": 6.238914689814962e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad82584973d0520c6413d732f42ff58e62845f5cbb51b8e6c61b5efa59935b29
+oid sha256:aa4ab0c6834a759e55baa287a48208abf39c778ed277af3b0afe1b1b96d8b552
 size 449471589